Solving the problem of Optical Character Recognition (OCR) on printed text for Latin and its derivative scripts can now be considered settled due to the volumes of research done on English and other High-Resourced Languages (HRL). However, for Low-Resourced Languages (LRL) that use unique scripts, it remains an open problem. This study presents a comparative analysis of the zero-shot performance of six distinct OCR engines on two LRLs: Sinhala and Tamil. The selected engines include both commercial and open-source systems, aiming to evaluate the strengths of each category. The Cloud Vision API, Surya, Document AI, and Tesseract were evaluated for both Sinhala and Tamil, while Subasa OCR and EasyOCR were examined for only one language due to their limitations. The performance of these systems was rigorously analysed using five measurement techniques to assess accuracy at both the character and word levels. According to the findings, Surya delivered the best performance for Sinhala across all metrics, with a WER of 2.61%. Conversely, Document AI excelled across all metrics for Tamil, highlighted by a very low CER of 0.78%. In addition to the above analysis, we also introduce a novel synthetic Tamil OCR benchmarking dataset.

Handwritten text recognition (HTR) remains a challenging task, particularly for multi-page documents where pages share common formatting and contextual features. While modern optical character recognition (OCR) engines are proficient with printed text, their performance on handwriting is limited, often requiring costly labeled data for fine-tuning. In this paper, we explore the use of multi-modal large language models (MLLMs) for transcribing multi-page handwritten documents in a zero-shot setting. We investigate various configurations of commercial OCR engines and MLLMs, utilizing the latter both as end-to-end transcribers and as post-processors, with and without image components. We propose a novel method, + FIRST PAGE, which enhances MLLM transcription by providing the OCR output of the entire document along with just the first page image . This approach leverages shared document features without incurring the high cost of processing all images. Experiments on a multi-page version of the IAM Handwriting Database demonstrate that + FIRST PAGE improves transcription accuracy, balances cost with performance, and even enhances results on out-of-sample text by extrapolating formatting and OCR error patterns from a single page. Introduction A significant proportion of all human-written text exists only in the form of physical handwritten documents.

This paper introduces LMRPA, a novel Large Model-Driven Robotic Process Automation (RPA) model designed to greatly improve the efficiency and speed of Optical Character Recognition (OCR) tasks. Traditional RPA platforms often suffer from performance bottlenecks when handling high-volume repetitive processes like OCR, leading to a less efficient and more time-consuming process. LMRPA allows the integration of Large Language Models (LLMs) to improve the accuracy and readability of extracted text, overcoming the challenges posed by ambiguous characters and complex text structures.Extensive benchmarks were conducted comparing LMRPA to leading RPA platforms, including UiPath and Automation Anywhere, using OCR engines like Tesseract and DocTR. The results are that LMRPA achieves superior performance, cutting the processing times by up to 52\%. For instance, in Batch 2 of the Tesseract OCR task, LMRPA completed the process in 9.8 seconds, where UiPath finished in 18.1 seconds and Automation Anywhere finished in 18.7 seconds. Similar improvements were observed with DocTR, where LMRPA outperformed other automation tools conducting the same process by completing tasks in 12.7 seconds, while competitors took over 20 seconds to do the same. These findings highlight the potential of LMRPA to revolutionize OCR-driven automation processes, offering a more efficient and effective alternative solution to the existing state-of-the-art RPA models.

Automating high-volume unstructured data processing is essential for operational efficiency. Optical Character Recognition (OCR) is critical but often struggles with accuracy and efficiency in complex layouts and ambiguous text. These challenges are especially pronounced in large-scale tasks requiring both speed and precision. This paper introduces LMV-RPA, a Large Model Voting-based Robotic Process Automation system to enhance OCR workflows. LMV-RPA integrates outputs from OCR engines such as Paddle OCR, Tesseract OCR, Easy OCR, and DocTR with Large Language Models (LLMs) like LLaMA 3 and Gemini-1.5-pro. Using a majority voting mechanism, it processes OCR outputs into structured JSON formats, improving accuracy, particularly in complex layouts. The multi-phase pipeline processes text extracted by OCR engines through LLMs, combining results to ensure the most accurate outputs. LMV-RPA achieves 99 percent accuracy in OCR tasks, surpassing baseline models with 94 percent, while reducing processing time by 80 percent. Benchmark evaluations confirm its scalability and demonstrate that LMV-RPA offers a faster, more reliable, and efficient solution for automating large-scale document processing tasks.

We propose a new approach for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes. Two steps, namely line splitting and line clustering, are performed to extract paragraphs from the lines in OCR results. Each step uses a beta-skeleton graph constructed from bounding boxes, where the graph edges provide efficient support for graph convolution operations. With only pure layout input features, the GCN model size is 3~4 orders of magnitude smaller compared to R-CNN based models, while achieving comparable or better accuracies on PubLayNet and other datasets. Furthermore, the GCN models show good generalization from synthetic training data to real-world images, and good adaptivity for variable document styles.

Key-value pair extraction is at the heart of document processing. To understand how it works and what it brings, it's necessary to explain the concepts behind the words. We will then see why it's so important for companies and organizations of all industries. KVPs are two related data items, a key, and a value. The key defines the data and is fixed, and the value is variable and describes the key.

Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR engines may introduce errors and inputs to downstream NLP models become noisy. Despite that pre-trained models achieve state-of-the-art performance in many NLP benchmarks, we prove that they are not robust to noisy texts generated by real OCR engines. This greatly limits the application of NLP models in real-world scenarios. In order to improve model performance on noisy OCR transcripts, it is natural to train the NLP model on labelled noisy texts. However, in most cases there are only labelled clean texts. Since there is no handwritten pictures corresponding to the text, it is impossible to directly use the recognition model to obtain noisy labelled data. Human resources can be employed to copy texts and take pictures, but it is extremely expensive considering the size of data for model training. Consequently, we are interested in making NLP models intrinsically robust to OCR errors in a low resource manner. We propose a novel robust training framework which 1) employs simple but effective methods to directly simulate natural OCR noises from clean texts and 2) iteratively mines the hard examples from a large number of simulated samples for optimal performance. 3) To make our model learn noise-invariant representations, a stability loss is employed. Experiments on three real-world datasets show that the proposed framework boosts the robustness of pre-trained models by a large margin. We believe that this work can greatly promote the application of NLP models in actual scenarios, although the algorithm we use is simple and straightforward. We make our codes and three datasets publicly available\footnote{https://github.com/tal-ai/Robust-learning-MSSHEM}.

Data entry may sound like a long and boring task but it is one of the most significant of the business operations. Data security is highest of concern as businesses are built on this. In order to secure and manage the data, organizations are required to enter all their data on their online systems. However, entering data of individual customers from its physical form into the online system may take hours of manual labor. In order to enhance this data entry procedure, OCR technology is developed.

Tracking users' activities on the World Wide Web (WWW) allows researchers to analyze each user's internet behavior as time passes and for the amount of time spent on a particular domain. This analysis can be used in research design, as researchers may access to their participant's behaviors while browsing the web. Web search behavior has been a subject of interest because of its real-world applications in marketing, digital advertisement, and identifying potential threats online. In this paper, we present an image-processing based method to extract domains which are visited by a participant over multiple browsers during a lab session. This method could provide another way to collect users' activities during an online session given that the session recorder collected the data.